Machine learning-based pavement crack detection, classification, and characterization: a review

Aug 4, 2026

Upload by Noah

Pavement crack detection, classification, and characterization directly impact safe road conditions, yet manual inspection is slow, expensive, and risky for inspectors. This review surveys state-of-the-art machine vision and machine learning pipelines for identifying cracks in pavement imagery. It compares both traditional methods and AI approaches, emphasizing feature extraction via image processing, common models such as support vector machines and neural networks, and deep learning advances. The article also summarizes data collection strategies, available datasets, model comparisons, and remaining open challenges to support future research and improved maintenance efficiency.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Key challenges in pavement inspection

Machine vision and ML pipeline overview

Feature extraction and traditional methods

AI models: SVM and neural networks

Deep learning advancements

Data sources, datasets, and model comparisons

Open challenges and future research directions

11/6/23 , 8:50 AM Scopus-Print Document Documents Ashraf, A.a , Sophian, A. b , Shafie, A.A. b , Gunawan, T.S.a , Ismail, N. N.c Machine learning-based pavement crack detection, classification, and characterization: a review (2023) Bulletin of Electrical Engineering and Informatics , 12 (6), pp. 3601-3619. DOI: 10.11591/eei.v12i6 .5345 a Department of Electrical and Computer Engineering, International Islamic University Malaysia, Kuala Lumpur, Malaysia b Department of Mechatronics Engineering, International Islamic University Malaysia, Kuala Lumpur, Malaysia c School of Civil Engineering, College of Engineering, Universiti Teknologi MARA, Shah Alam, Malaysia Abstract The detection, classification, and characterization of pavement cracks are critical for maintaining safe road conditions. However, traditional manual inspection methods are slow, costly, and pose risks to inspectors. To address these issues, this article provides a comprehensive overview of state-of-the-art machine vision and machine learning-based techniques for pavement crack detection, classification, and characterization. The paper explores the process flow of these systems, including both machine learning and traditional methodologies. The paper focuses on popular artificial intelligence (AI) techniques like support vector machines (SVM) and neural networks. It underscores the significance of utilizing image processing methods for feature extraction in order to detect cracks. The paper also discusses significant advancements made through deep learning strategies. The main objectives of this research are to improve efficiency and effectiveness in pavement crack detection, reduce inspection costs, and enhance safety. Additionally, the article presents data gathering approaches, various datasets for developing road crack detection models, and compares different models to demonstrate their advantages and limitations. Finally, the paper identifies open challenges in the field and provides valuable insights for future research and development efforts. Overall, this paper highlights the potential of AI-based techniques to revolutionize pavement maintenance practices and significantly improve road safety. © 2023, Institute of Advanced Engineering and Science. All rights reserved. Author Keywords Deep learning; Image processing; Machine learning; Machine vision; Pavement cracks Funding details Ministry of Higher Education, MalaysiaMOHEFRGS/1/2021/TK02/UIAM/02/4 The authors wish to acknowledge the support provided by the Malaysian Ministry of Higher Education (MOHE) through the Fundamental Research Grant Scheme, FRGS/1/2021/TK02/UIAM/02/4, References Feng, X. Pavement crack detection and segmentation method based on improved deep learning fusion model (2020) Mathematical Problems in Engineering , 2020, pp. 1-22. Dong, Z. Rapid detection methods for asphalt pavement thicknesses and defects by a vehicle-mounted ground penetrating radar (GPR) system (2016) Sensors, 16 (12), pp. 1-18. He, G. , Xie, Y. , Zhang, B. Expressways, GDP, and the environment: the case of China (2020) Journal of Development Economics , 145, p. 102485. Zhou, S. , Liang, Y. , Wan, J. , Li, S. Z. Facial expression recognition based on multiscale CNNs (2016) Biometric Recognition , pp. 503-510. Cham: Springer -Jin, C. Y. , Wooram, C. , Oral, B. Deep learning-based crack damage detection using convolutional neural networks [https://www.scopus.com/citation/print.uri?origin=recordpage&sid=&src=s&stateKey=OFD_1711003450&eid=2-s2.0-85174618118&sort=&clicked](https://www.scopus.com/citation/print.uri?origin=recordpage&sid=&src=s&stateKey=OFD_1711003450&eid=2-s2.0-85174618118&sort=&clicked)… 1/8 11/6/23 , 8:50 AM Scopus-Print Document (2017) Computer-aided civil and infrastructure engineering , 32 (5), pp. 361-378. Zou, Q. , Zhang, Z. , Li, Q. , Qi, X. , Wang, Q. , Wang, S. DeepCrack: learning hierarchical convolutional features for cra

FAQs

Why is pavement crack inspection difficult with traditional manual methods?

Manual inspection is slow and costly, and it also exposes inspectors to safety risks during field evaluation.

What types of techniques are reviewed for pavement crack detection and analysis?

The review covers machine vision and machine learning pipelines, including both traditional methodologies and AI methods such as support vector machines and neural networks.

How does the paper address data and evaluation for crack detection models?

It presents data gathering approaches, discusses various datasets used to develop road crack detection models, and compares different models to highlight their advantages and limitations.

Aug 4, 2026

Upload by Noah